Use of the k-nearest neighbour and its analysis for fall detection on Systems on a Chip for multiple datasets

Fall of an elderly person often leads to serious injuries and death. Many falls occur in the home environment, and hence a reliable fall detection system that can raise alarms with minimum latency is a necessity. Wrist-worn accelerometer-based fall detection systems and multiple datasets are availab...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Acta IMEKO Ročník 12; číslo 3; s. 1 - 11
Hlavní autoři: Nandi, Purab, Anupama, K. R., Agarwal, Himanish, Jain, Arav, Paliwal, Siddharth
Médium: Journal Article
Jazyk:angličtina
Vydáno: 18.09.2023
ISSN:0237-028X, 2221-870X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Fall of an elderly person often leads to serious injuries and death. Many falls occur in the home environment, and hence a reliable fall detection system that can raise alarms with minimum latency is a necessity. Wrist-worn accelerometer-based fall detection systems and multiple datasets are available, but no attempt has been made to analyze the accuracy and precision. Wherever the comparison does exist, it has been run on a cloud. No analysis of the models, convergence, and dataset analysis on Systems on a Chip (SoCs) has ever been attempted. In this paper, we attempt to present why Machine Learning (ML) algorithms in their current state cannot be run on existing SoCs. We have used Snapdragon 410c SoC to do our analytics. In this paper, we have used the kth-nearest neighbour to prove that ML cannot be directly run on SoCs. We have looked at the effect of distance metrics and neighbors as well as the effect of feature extraction on the accuracies and the latencies. In this paper, we establish the need for model compression and data pruning for fall detection using ML/Deep Learning algorithms on SoCs. We have done this by analyzing various datasets on varying architectural parameters.
AbstractList Fall of an elderly person often leads to serious injuries and death. Many falls occur in the home environment, and hence a reliable fall detection system that can raise alarms with minimum latency is a necessity. Wrist-worn accelerometer-based fall detection systems and multiple datasets are available, but no attempt has been made to analyze the accuracy and precision. Wherever the comparison does exist, it has been run on a cloud. No analysis of the models, convergence, and dataset analysis on Systems on a Chip (SoCs) has ever been attempted. In this paper, we attempt to present why Machine Learning (ML) algorithms in their current state cannot be run on existing SoCs. We have used Snapdragon 410c SoC to do our analytics. In this paper, we have used the kth-nearest neighbour to prove that ML cannot be directly run on SoCs. We have looked at the effect of distance metrics and neighbors as well as the effect of feature extraction on the accuracies and the latencies. In this paper, we establish the need for model compression and data pruning for fall detection using ML/Deep Learning algorithms on SoCs. We have done this by analyzing various datasets on varying architectural parameters.
Author Anupama, K. R.
Paliwal, Siddharth
Agarwal, Himanish
Nandi, Purab
Jain, Arav
Author_xml – sequence: 1
  givenname: Purab
  surname: Nandi
  fullname: Nandi, Purab
– sequence: 2
  givenname: K. R.
  surname: Anupama
  fullname: Anupama, K. R.
– sequence: 3
  givenname: Himanish
  surname: Agarwal
  fullname: Agarwal, Himanish
– sequence: 4
  givenname: Arav
  surname: Jain
  fullname: Jain, Arav
– sequence: 5
  givenname: Siddharth
  surname: Paliwal
  fullname: Paliwal, Siddharth
BookMark eNo9kMtqwzAUREVJoWmaTyjoB5zq4Ye8LKEvCHTRBrIzV_J1I2JbQVcp5O-bpKUwMLOYmcW5ZZMxjMjYvRQLJYXMH8Al8APuwuJbKq8XMjf1FZsqpWRmKrGZsKlQusqEMpsbNifyVhSyFLmqyykb1oQ8dDxtke-yESEiJT6i_9racIgcxpb7RCeH_kieeBci76DveYsJXfJh5Cd9HCnhQOcIfLn1-0tvOPTJ73vkLSQgTHTHrk9bwvmfz9j6-elz-Zqt3l_elo-rzMlS1xkoUboS8s5ap6UoC5urHI1RRrRFZatK6Q5bKHRlRFEbpVEjKAdoaqtbW-sZK35_XQxEEbtmH_0A8dhI0VywNf_Ymgu25oxN_wDJfGdT
ContentType Journal Article
DBID AAYXX
CITATION
DOI 10.21014/actaimeko.v12i3.1489
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList CrossRef
DeliveryMethod fulltext_linktorsrc
EISSN 2221-870X
EndPage 11
ExternalDocumentID 10_21014_actaimeko_v12i3_1489
GroupedDBID AAYXX
ALMA_UNASSIGNED_HOLDINGS
CITATION
GROUPED_DOAJ
OK1
ID FETCH-LOGICAL-c1639-a206c6a4fbbc31065b424e88280d57b7723feda5378059823e3ea2cae89b3db93
ISSN 0237-028X
IngestDate Sat Nov 29 02:26:52 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 3
Language English
License https://creativecommons.org/licenses/by/4.0
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c1639-a206c6a4fbbc31065b424e88280d57b7723feda5378059823e3ea2cae89b3db93
OpenAccessLink https://acta.imeko.org/index.php/acta-imeko/article/download/1489/2867
PageCount 11
ParticipantIDs crossref_primary_10_21014_actaimeko_v12i3_1489
PublicationCentury 2000
PublicationDate 2023-09-18
PublicationDateYYYYMMDD 2023-09-18
PublicationDate_xml – month: 09
  year: 2023
  text: 2023-09-18
  day: 18
PublicationDecade 2020
PublicationTitle Acta IMEKO
PublicationYear 2023
SSID ssib051604296
ssj0002140127
Score 2.2490351
Snippet Fall of an elderly person often leads to serious injuries and death. Many falls occur in the home environment, and hence a reliable fall detection system that...
SourceID crossref
SourceType Index Database
StartPage 1
Title Use of the k-nearest neighbour and its analysis for fall detection on Systems on a Chip for multiple datasets
Volume 12
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2221-870X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002140127
  issn: 0237-028X
  databaseCode: DOA
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2221-870X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib051604296
  issn: 0237-028X
  databaseCode: M~E
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1La9tAEF7cNIdeSktb0lfYQ29GjrSrx-6xBIf0kbSUBHwTu9KqmMSykWQ3p_6f_svM7FobJYTSHApGLIM8SJ7P89rZGUI-8DgVFWbuIfIqgzjJdCBinQYxmAvJyzLSTtJfs9NTMZvJ76PRn_4szOYyq2txdSVX_1XUQANh49HZB4jbMwUCrEHocAWxw_WfBH_e-o3_i6DGFrVtN64xA4oJTL9ZoPpuJFhnWOEGdWk64waHow5xncxxqbBeY2Xv8-WHWFjaGtcFyjexLTo1_nQy_fLNZ5jxzIz1U9eN0jcZh_VKLdxRtMn4x8TTf6rml3LNtefYlqP1qerPatvqoFGbYZ6CcSyqGKpWIGUBeDMzZ3ksDZyTCPRxOLulj9kAd3ygXKOBlXYa-q7-Zzh5GK0bvPB8YS6Wk03E5hzMgZtTdLvf9h076KsTIS6yjHLPJrdscmTziDxmWSKxevDk97RXXUmUomVPfXqPYeDqBgb37-3Oj1nOB_c94MAzGrg4Z8_I021sQj86TD0nI1O_IAvAE11WFPBEPZ6oxxMFEVPAE-3xRAEnFPFEPZ4ofLZ4wqWiiCd7X48n2uPpJTk_mp4dHgfbGR1BAZ68DBQL0yJVcaV1AZFCmuiYxQbCNhGW8MeH2I1XplQJx9kZUjBuuFGsUEZIzUst-SuyUy9rs0eo1NgOkKeJhDBCRKHmFRhfaUDNhIWI1Gsy6X-ffOVaseR_FdWbh37hLXlyg9x3ZKdr1uY92S023bxt9m26Zt-K_RqoIocA
linkProvider ISSN International Centre
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Use+of+the+k-nearest+neighbour+and+its+analysis+for+fall+detection+on+Systems+on+a+Chip+for+multiple+datasets&rft.jtitle=Acta+IMEKO&rft.au=Nandi%2C+Purab&rft.au=Anupama%2C+K.+R.&rft.au=Agarwal%2C+Himanish&rft.au=Jain%2C+Arav&rft.date=2023-09-18&rft.issn=0237-028X&rft.eissn=2221-870X&rft.volume=12&rft.issue=3&rft.spage=1&rft.epage=11&rft_id=info:doi/10.21014%2Factaimeko.v12i3.1489&rft.externalDBID=n%2Fa&rft.externalDocID=10_21014_actaimeko_v12i3_1489
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0237-028X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0237-028X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0237-028X&client=summon